© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204549
    Prev
    Next
    INDEX
    Explanations

    driven consumer, suitable for, annoying or

    np_acts-logits-general · gemini-2.5-flash-lite

    hypothetical questions and ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <0x99>
    0.46
    
    0.43
    <0x86>
    0.41
    <0x87>
    0.41
     chile
    0.41
    file
    0.40
     handleError
    0.40
    గో
    0.39
     RULE
    0.39
    샨
    0.39
    POSITIVE LOGITS
     wskaz
    0.45
     Blank
    0.45
     oiseaux
    0.45
     traslado
    0.44
     assinatura
    0.43
     engage
    0.43
    ர்ஸ்
    0.42
     illusory
    0.41
    assistance
    0.40
     झु
    0.40
    Activations Density 0.001%

    No Known Activations